{"id":"https://openalex.org/W2805704837","doi":"https://doi.org/10.1007/s41019-018-0067-3","title":"Exploiting Multi-Category Characteristics and Unified Framework to Extract Web Content","display_name":"Exploiting Multi-Category Characteristics and Unified Framework to Extract Web Content","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2805704837","doi":"https://doi.org/10.1007/s41019-018-0067-3","mag":"2805704837"},"language":"en","primary_location":{"id":"doi:10.1007/s41019-018-0067-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-018-0067-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-018-0067-3.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s41019-018-0067-3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100434273","display_name":"Jingwei Zhang","orcid":"https://orcid.org/0000-0002-7907-2853"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwei Zhang","raw_affiliation_strings":["Guangxi Cooperative Innovation Center of Cloud Computing and Big Data, Guilin University of Electronic Technology, Guilin, 541004, China","Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, 541004, China"],"raw_orcid":"https://orcid.org/0000-0002-7907-2853","affiliations":[{"raw_affiliation_string":"Guangxi Cooperative Innovation Center of Cloud Computing and Big Data, Guilin University of Electronic Technology, Guilin, 541004, China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, 541004, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391116","display_name":"Qian Wang","orcid":"https://orcid.org/0000-0002-8967-8525"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Wang","raw_affiliation_strings":["Guangxi Cooperative Innovation Center of Cloud Computing and Big Data, Guilin University of Electronic Technology, Guilin, 541004, China","Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, 541004, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Cooperative Innovation Center of Cloud Computing and Big Data, Guilin University of Electronic Technology, Guilin, 541004, China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, 541004, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qing Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qing Yang","raw_affiliation_strings":["Guangxi Cooperative Innovation Center of Cloud Computing and Big Data, Guilin University of Electronic Technology, Guilin, 541004, China","Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, 541004, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Cooperative Innovation Center of Cloud Computing and Big Data, Guilin University of Electronic Technology, Guilin, 541004, China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, 541004, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032749574","display_name":"Rui Zhou","orcid":"https://orcid.org/0000-0001-6807-4362"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rui Zhou","raw_affiliation_strings":["Faculty of Science, Engineering and Technology, Swinburne University of Technology, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science, Engineering and Technology, Swinburne University of Technology, Melbourne, Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049750015","display_name":"Yanchun Zhang","orcid":"https://orcid.org/0000-0002-5094-5980"},"institutions":[{"id":"https://openalex.org/I71270174","display_name":"Victoria University","ror":"https://ror.org/04j757h98","country_code":"AU","type":"education","lineage":["https://openalex.org/I71270174"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yanchun Zhang","raw_affiliation_strings":["Centre for Applied Informatics, Victoria University, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Applied Informatics, Victoria University, Melbourne, Australia","institution_ids":["https://openalex.org/I71270174"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5343935"],"apc_list":null,"apc_paid":null,"fwci":2.4246,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91912529,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":"2","first_page":"101","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9535999894142151,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9408000111579895,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8490673899650574},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6925408840179443},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5850214958190918},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5142399668693542},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5096080303192139},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.47673356533050537},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.47553062438964844},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.4714166820049286},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.46403858065605164},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.4606056809425354},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4041041135787964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8490673899650574},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6925408840179443},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5850214958190918},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5142399668693542},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5096080303192139},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.47673356533050537},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.47553062438964844},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.4714166820049286},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.46403858065605164},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.4606056809425354},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4041041135787964},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s41019-018-0067-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-018-0067-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-018-0067-3.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},{"id":"pmh:oai:eprints.vu.edu.au:38383","is_oa":true,"landing_page_url":"https://vuir.vu.edu.au/38383/","pdf_url":"https://vuir.vu.edu.au/38383/","source":{"id":"https://openalex.org/S4306400215","display_name":"Victoria University Research Repository (Victoria University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I41156924","host_organization_name":"Victoria University of Wellington","host_organization_lineage":["https://openalex.org/I41156924"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:6abd6d9fee364a8cab054851e8ccbc82","is_oa":false,"landing_page_url":"https://doaj.org/article/6abd6d9fee364a8cab054851e8ccbc82","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science and Engineering, Vol 3, Iss 2, Pp 101-114 (2018)","raw_type":"article"},{"id":"pmh:oai:researchbank.swinburne.edu.au:9b72963a-a97b-4b62-b006-3e428aa86701/1","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.3/446660","pdf_url":null,"source":{"id":"https://openalex.org/S4306401157","display_name":"Swinburne Research Bank (Swinburne University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I57093077","host_organization_name":"Swinburne University of Technology","host_organization_lineage":["https://openalex.org/I57093077"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science and Engineering, Vol. 3, no. 2 (Jun 2018), pp. 101-114","raw_type":null}],"best_oa_location":{"id":"doi:10.1007/s41019-018-0067-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-018-0067-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-018-0067-3.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2286835249","display_name":null,"funder_award_id":"61662015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2899483951","display_name":null,"funder_award_id":"U1711263","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"},{"id":"https://openalex.org/G506509722","display_name":null,"funder_award_id":"2017GXNSFAA198035","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"},{"id":"https://openalex.org/G6546932133","display_name":null,"funder_award_id":"U1711263","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6740435788","display_name":null,"funder_award_id":"61462017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7706890246","display_name":null,"funder_award_id":"61363005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G796562679","display_name":null,"funder_award_id":"U1501252","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"},{"id":"https://openalex.org/G8698608195","display_name":null,"funder_award_id":"U1501252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322768","display_name":"Natural Science Foundation of Guangxi Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2805704837.pdf","grobid_xml":"https://content.openalex.org/works/W2805704837.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W100562005","https://openalex.org/W146288251","https://openalex.org/W1566513354","https://openalex.org/W1706374111","https://openalex.org/W1785837166","https://openalex.org/W1832894994","https://openalex.org/W1877467562","https://openalex.org/W2003204742","https://openalex.org/W2007278884","https://openalex.org/W2012575882","https://openalex.org/W2012833704","https://openalex.org/W2019441211","https://openalex.org/W2019577381","https://openalex.org/W2049488566","https://openalex.org/W2087406717","https://openalex.org/W2104086170","https://openalex.org/W2113771144","https://openalex.org/W2129595335","https://openalex.org/W2135767707","https://openalex.org/W2158051716","https://openalex.org/W2166817967","https://openalex.org/W2167859982","https://openalex.org/W2216972693","https://openalex.org/W2296045323","https://openalex.org/W2340809461","https://openalex.org/W2421306863","https://openalex.org/W2438218466","https://openalex.org/W2474797713","https://openalex.org/W2507783418","https://openalex.org/W2616545289","https://openalex.org/W3146013852","https://openalex.org/W4240555197"],"related_works":["https://openalex.org/W1495666889","https://openalex.org/W2963140294","https://openalex.org/W2100071482","https://openalex.org/W2729360854","https://openalex.org/W2151311386","https://openalex.org/W2780890200","https://openalex.org/W2165565716","https://openalex.org/W4249203355","https://openalex.org/W2065605022","https://openalex.org/W2367158473"],"abstract_inverted_index":{"Extracting":[0],"web":[1,11,50,58,79,89,124,143,178],"content":[2,80,118,156],"is":[3],"to":[4,36,39,67,91,105,163],"obtain":[5],"the":[6,47,62,129,165],"required":[7],"data":[8],"embedded":[9],"in":[10,57,87],"pages,":[12],"usually":[13],"including":[14,114,184],"structured":[15,94,161],"records,":[16,162],"such":[17,24],"as":[18,25],"product":[19],"information,":[20,117],"and":[21,38,52,71,96,157,187,200],"text":[22,97,116,155],"content,":[23],"news.":[26],"Web":[27],"pages":[28,51,59],"use":[29],"a":[30,77,102],"large":[31],"number":[32],"of":[33,49,55,108,120],"HTML":[34,121],"tags":[35],"organize":[37],"present":[40],"various":[41,88],"information.":[42],"Both":[43],"knowing":[44],"little":[45],"about":[46],"structures":[48],"mixing":[53],"kinds":[54,107],"information":[56],"are":[60,132],"making":[61],"extraction":[63,69,72,81,112,136,139,166,172,182,193,198,201],"process":[64],"very":[65],"challenging":[66],"guarantee":[68],"performance":[70],"adaptability.":[73,202],"This":[74],"study":[75],"proposes":[76],"unified":[78],"framework":[82,137],"that":[83,190],"can":[84,195],"be":[85],"applied":[86],"environments":[90],"extract":[92],"both":[93,170],"records":[95],"content.":[98],"First,":[99],"we":[100,146],"construct":[101],"characteristic":[103],"container":[104],"hold":[106],"characteristics":[109,131],"related":[110],"with":[111,180],"objectives,":[113],"visual":[115],"semantics(instead":[119],"tag":[122],"semantics),":[123],"page":[125],"structures,":[126],"etc.":[127],"Second,":[128],"above":[130],"integrated":[133],"into":[134],"an":[135],"for":[138,153,160],"decisions":[140],"on":[141,176],"different":[142,149],"sites.":[144],"Especially,":[145],"put":[147],"forward":[148],"strategies,":[150],"path":[151],"aggregation":[152],"extracting":[154],"HMM":[158],"model":[159],"locate":[164],"area":[167],"by":[168],"exploiting":[169],"those":[171],"characteristics.":[173],"Comparative":[174],"experiments":[175],"multiple":[177],"sites":[179],"popular":[181],"methods,":[183],"CETR,":[185],"CETD":[186],"CNBE,":[188],"show":[189],"our":[191],"proposed":[192],"method":[194],"provide":[196],"better":[197],"precision":[199]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-15T05:50:42.429089","created_date":"2025-10-10T00:00:00"}
